Advances in Cuffless Continuous Blood Pressure Monitoring Technology Based on PPG Signals

Qin, Caijie; Wang, Xiaohua; Xu, Guangjun; Ma, Xibo

doi:10.1155/2022/8094351

Cited by 5 publications

(2 citation statements)

References 92 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PPG and PWV will be further discussed later in the article. By using a specific range of light sources, PPG detects periodic blood volume changes in tissues throughout the heart cycle in a noninvasive way [ 62 ].…”

Section: Novel Technologiesmentioning

confidence: 99%

History and evolution of blood pressure measurement

Noh,

Kim,

Kang

et al. 2024

Clin Hypertens

View full text Add to dashboard Cite

Hypertension is the leading cause of morbidity and mortality worldwide. Hypertension mostly accompanies no symptoms, and therefore blood pressure (BP) measurement is the only way for early recognition and timely treatment. Methods for BP measurement have a long history of development and improvement. Invasive method via arterial cannulation was first proven possible in the 1800’s. Subsequent scientific progress led to the development of the auscultatory method, also known as Korotkoff’ sound, and the oscillometric method, which enabled clinically available BP measurement. However, hypertension management status is still poor. Globally, less than half of adults are aware of their hypertension diagnosis, and only one-third of them being treated are under control. Novel methods are actively investigated thanks to technological advances such as sensors and machine learning in addition to the clinical needs for easier and more convenient BP measurement. Each method adopts different technologies with its own specific advantages and disadvantages. Promises of novel methods include comprehensive information on out-of-office BP capturing dynamic short-term and long-term fluctuations. However, there are still pitfalls such as the need for regular calibration since most novel methods capture relative BP changes rather than an absolute value. In addition, there is growing concern on their accuracy and precision as conventional validation protocols are inappropriate for cuffless continuous methods. In this article, we provide a comprehensive overview of the past and present of BP measurement methods. Novel and emerging technologies are also introduced with respect to their potential applications and limitations. Graphical Abstract

show abstract

Section: Novel Technologiesmentioning

confidence: 99%

History and evolution of blood pressure measurement

Noh,

Kim,

Kang

et al. 2024

Clin Hypertens

View full text Add to dashboard Cite

show abstract

“…Additionally, it indicates how closely the data is related to the mean. The SD value was used as an indicator of error dispersion [43]. The lower the SD value, the closer the data is to the average value.…”

Section: Association For the Advancement Of Medical Instrumentation (...mentioning

confidence: 99%

PPG Signals-Based Blood-Pressure Estimation Using Grid Search in Hyperparameter Optimization of CNN–LSTM

Fuadah

Jeong

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Researchers commonly use continuous noninvasive blood-pressure measurement (cNIBP) based on photoplethysmography (PPG) signals to monitor blood pressure conveniently. However, the performance of the system still needs to be improved. Accuracy and precision in blood-pressure measurements are critical factors in diagnosing and managing patients’ health conditions. Therefore, we propose a convolutional long short-term memory neural network (CNN–LSTM) with grid search ability, which provides a robust blood-pressure estimation system by extracting meaningful information from PPG signals and reducing the complexity of hyperparameter optimization in the proposed model. The multiparameter intelligent monitoring for intensive care III (MIMIC III) dataset obtained PPG and arterial-blood-pressure (ABP) signals. We obtained 75,226 signal segments, with 60,180 signals allocated for training data, 12,030 signals allocated for the validation set, and 15,045 signals allocated for the test data. During training, we applied five-fold cross-validation with a grid-search method to select the best model and determine the optimal hyperparameter settings. The optimized configuration of the CNN–LSTM layers consisted of five convolutional layers, one long short-term memory (LSTM) layer, and two fully connected layers for blood-pressure estimation. This study successfully achieved good accuracy in assessing both systolic blood pressure (SBP) and diastolic blood pressure (DBP) by calculating the standard deviation (SD) and the mean absolute error (MAE), resulting in values of 7.89 ± 3.79 and 5.34 ± 2.89 mmHg, respectively. The optimal configuration of the CNN–LSTM provided satisfactory performance according to the standards set by the British Hypertension Society (BHS), the Association for the Advancement of Medical Instrumentation (AAMI), and the Institute of Electrical and Electronics Engineers (IEEE) for blood-pressure monitoring devices.

show abstract